# Evaluating the Impact of Intensity Normalization on MR Image Synthesis

## TL;DR

This paper investigates how different intensity normalization techniques affect MR image synthesis, demonstrating that normalization significantly improves synthesis quality and is essential for deep learning methods.

## Contribution

The study systematically evaluates seven normalization algorithms across three synthesis methods, highlighting the importance of normalization in MR image synthesis.

## Key findings

- Normalization improves synthesis results across methods
- Normalization is crucial for deep learning-based synthesis
- Different normalization algorithms have varying impacts

## Abstract

Image synthesis learns a transformation from the intensity features of an input image to yield a different tissue contrast of the output image. This process has been shown to have application in many medical image analysis tasks including imputation, registration, and segmentation. To carry out synthesis, the intensities of the input images are typically scaled--i.e., normalized--both in training to learn the transformation and in testing when applying the transformation, but it is not presently known what type of input scaling is optimal. In this paper, we consider seven different intensity normalization algorithms and three different synthesis methods to evaluate the impact of normalization. Our experiments demonstrate that intensity normalization as a preprocessing step improves the synthesis results across all investigated synthesis algorithms. Furthermore, we show evidence that suggests intensity normalization is vital for successful deep learning-based MR image synthesis.